A cost minimization approach to human behavior recognition
Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
An optimum accelerometer configuration and simple algorithm for accurately detecting falls
BioMed'06 Proceedings of the 24th IASTED international conference on Biomedical engineering
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Extracting a diagnostic gait signature
Pattern Recognition
ISWC '07 Proceedings of the 2007 11th IEEE International Symposium on Wearable Computers
Automatic detection of human fall in video
PReMI'07 Proceedings of the 2nd international conference on Pattern recognition and machine intelligence
Nomadic gestures: A technique for reusing gesture commands for frequent ambient interactions
Journal of Ambient Intelligence and Smart Environments
Hi-index | 0.00 |
A system for automatic identification of gait patterns related to health problems of elderly for the purpose of supporting their independent living is proposed in this paper. The gait of the user is captured with the motion capture system, which consists of tags attached to the body and sensors situated in the apartment. Position of the tags is acquired by the sensors and the resulting time series of position coordinates are analyzed with machine learning algorithms in order to identify the specific health problem. We propose novel features for training a machine learning classifier that classifies the user's gait into: i) normal, ii) with hemiplegia, iii) with Parkinson's disease, iv) with pain in the back and v) with pain in the leg. Results show that naive Bayes needs more tags and less noise to reach classification accuracy of 98 % than random forest for 99 %.